Pose estimation model for recognizing instruments in intraluminal aortic intervention
10.13929/j.issn.1672-8475.2025.02.012
- VernacularTitle:姿态估计模型用于识别主动脉腔内介入器具
- Author:
Shangzhi WU
1
;
Qingsheng LU
Author Information
1. 上海理工大学健康科学与工程学院,上海 200093
- Publication Type:Journal Article
- Keywords:
endovascular procedures;
radiography;
deep learning;
pattern recognition,visual
- From:
Chinese Journal of Interventional Imaging and Therapy
2025;22(2):136-141
- CountryChina
- Language:Chinese
-
Abstract:
Objective To establish a pose estimation model for recognizing instruments in intraluminal aortic intervention and to evaluate its efficiency as well as clinical applicability.Methods Forty-eight digital subtraction angiography(DSA)video clips of 45 patients who underwent intraluminal aortic intervention by physician or robot-assisted physician were collected and preprocessed into one video with totally 10 220 frames.The frames were categorized into 5 levels of background complexity.A key dataset of 5 110 frames was selected from 10 220 frames after intermittent frame extraction and divided into training set(n=4 599)and validation set(n=511).The accumulative numbers of guidewires,catheters,guidewire tips and catheter tips with manual labels in training set were recorded.Feature extraction was performed via a backbone network of this model,and an optical flow tracking algorithm was combined to achieve key point tracking between consecutive frames.After frame-by-frame inference across all 10 220 frames,the confusion results in training set were calculated,while the accuracy was calculated in validation set,the inference speeds were record in all sets,and the results were compared with those of U-Net.Results In validation set,the mean accuracy of the model for recognizing guidewires and catheters was 0.832 and 0.808,respectively,better than those of U-Net(0.767 and 0.793).For physician-operated procedures,the average accuracy of this model for recognizing guidewires and catheters within chest aorta was 0.787 and 0.756,which within abdominal aortic was 0.826 and 0.806,respectively.For robot-assisted procedures,the average accuracy of this model for recognizing guidewires and catheters in validation set was 0.855 and 0.834,respectively.Under 5 descending levels of background complexity,the model achieved recognizing accuracies of 0.594,0.865,0.817,0.793 and 0.764 for guidewires,and of 0.626,0.847,0.795,0.739 and 0.694 for catheters.In training set,this model accumulatively correctly classified guidewires,catheters,guidewire tips and catheter tips in 7 971,7 026,7 551 and 7 533 ones,accumulatively missed classified guidewires,catheters,guidewire tips and catheter tips in 1 271,1 357,812 and 863 ones,respectively.For all 10 220 frames,the inference frame rate of this model was 20.66 frames per second.Conclusion The obtained pose estimation model demonstrated excellent accuracies for recognizing instruments in intraluminal aortic intervention with real-time processing capability,which was able for clinical application.
